您好，欢迎访问中国热带农业科学院 机构知识库！
中国热带农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Lightweight deep learning model for embedded systems efficiently predicts oil and protein content in rapeseed

文献类型： 外文期刊

作者： Guo, Mengshuai 1 ; Ma, Huifang 3 ; Lv, Xin 1 ; Wang, Dan 1 ; Fu, Li 1 ; He, Ping 1 ; Mei, Desheng 1 ; Chen, Hong 1 ; Wei, Fang 1 ;

作者机构： 1.Chinese Acad Agr Sci, Key Lab Oilseeds Proc, Hubei Key Lab Lipid Chem & Nutr, Minist Agr,Oil Crops Res Inst, Wuhan 430062, Hubei, Peoples R China

2.Hubei Hongshan Lab, Wuhan 430070, Hubei, Peoples R China

3.Chinese Acad Trop Agr Sci, Agr Prod Proc Res Inst, Zhanjiang 524001, Peoples R China

关键词： Rapeseed; Oil and protein; Content prediction; Deep learning; Computer vision; Real-time prediction

期刊名称：FOOD CHEMISTRY （ 影响因子：9.8； 五年影响因子：9.7 ）

ISSN： 0308-8146

年卷期： 2025 年 477 卷

页码：

收录情况： SCI

摘要： Conventional methods for determining protein and oil content in rapeseed are often time-consuming, laborintensive, and costly. In this study, a mobile application was developed using an optimized deep learning method for low-cost, non-destructive and real-time prediction of protein and oil content in rapeseed by inputting rapeseed images. Among the tested models, FasterNet-L showed the optimal performance, with predicted coefficients of determination (Rp2) of 0.9366 for oil content and 0.8828 for protein content. The mean square error of prediction (RMSEP) was 0.6982 and 0.6498, and the residual predictive deviation (RPD) was 3.88 and 2.92 for oil and protein content, respectively. Furthermore, three pruning methods were employed, and neural pruning via growth regularization proved to be the most effective, with a 13.18 % improvement in prediction speed and a 15.79 % reduction in model size. Finally, this method can be expanded and applied to other oilseed crops for rapid quality identification and detection.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国热带农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台